[R] AIC for robust regression

From: James Warren Shaw <jwshaw_at_uic.edu>
Date: Mon, 04 Apr 2011 16:39:04 -0500

I am interested in comparing the fit of robust (i.e., S and MM) and non-robust (i.e., OLS) estimators when applied to a particular data set. The paper entitled "A comparison of robust versions of the AIC based on M, S and MM-estimators" (available at:
http://ideas.repec.org/p/ner/leuven/urnhdl123456789-274771.html) presents formulas for robust Akaike information criteria (AIC) for the M, S, and MM estimators. Unfortunately, these omit the term {n + n*ln(2*pi)} that is included in the standard AIC formula used by R's AIC function. Would it be appropriate to either (1) include the term in the robust estimator formulas to make them comparable with the standard AIC formula or (2) omit the term from the standard AIC formula to make it comparable with the robust estimator formulas? All of the models I am comparing include the same independent and dependent variables. Only the estimator is being varied. Also, is anyone aware of an AIC analog that would be applicable to least trimmed squares estimation?  





James W. Shaw, Ph.D., Pharm.D., M.P.H.

Assistant Professor

Department of Pharmacy Administration 

College of Pharmacy

University of Illinois at Chicago

833 South Wood Street, M/C 871, Room 266

Chicago, IL 60612

Tel.: 312-355-5666

Fax: 312-996-0868

Mobile Tel.: 215-852-3045


	[[alternative HTML version deleted]]

R-help_at_r-project.org mailing list
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
Received on Mon 04 Apr 2011 - 21:42:35 GMT

Archive maintained by Robert King, hosted by the discipline of statistics at the University of Newcastle, Australia.
Archive generated by hypermail 2.2.0, at Mon 04 Apr 2011 - 22:10:27 GMT.

Mailing list information is available at https://stat.ethz.ch/mailman/listinfo/r-help. Please read the posting guide before posting to the list.

list of date sections of archive